Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.3541. Min Range: -5.3541

Max Act: 5.3541. Min Act: -0.0001

Data Index: 597539 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.9208. Min Act: -0.0001

Data Index: 938063 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.5017. Min Act: -0.0001

Data Index: 1294849 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.5758. Min Act: -0.0001

Data Index: 371202 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.9553. Min Act: -0.0001

Data Index: 660301 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7130. Min Act: -0.0001

Data Index: 174461 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.8611. Min Act: -0.0001

Data Index: 672149 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.5903. Min Act: -0.0001

Data Index: 346492 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.4231. Min Act: -0.0001

Data Index: 862698 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7298. Min Act: -0.0001

Data Index: 592764 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.4423. Min Act: -0.0001

Data Index: 1342192 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.0991. Min Act: -0.0000

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.5338. Min Act: -0.0001

Data Index: 955003 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.0981. Min Act: -0.0001

Data Index: 320323 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.1932. Min Act: -0.0001

Data Index: 80374 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 5.3541. Min Range: -5.3541

Max Act: 3.6812. Min Act: -0.0001

Data Index: 940159 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.1058. Min Act: -0.0001

Data Index: 860180 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.0983. Min Act: -0.0001

Data Index: 771766 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.4771. Min Act: -0.0001

Data Index: 497292 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 5.3541. Min Range: -5.3541

Max Act: 3.6289. Min Act: -0.0001

Data Index: 905195 (C4 (Web Text))

Max Activating Token Index: 917